Frequently asked questions
What is a tts program?
Lectura is a cloud text-to-speech API that converts text into audio files via a simple REST endpoint. You send text and receive an audio file. It is designed for schools and teachers to convert lesson text and announcements into audio without coding, using a straightforward interface compatible with standard SDKs.
How do I get an API key?
Sign up on the /get-api-key/ page using Google or an email and password. The page displays your API key, balance, and usage details. You can issue a new key at any time, which immediately invalidates the old one. Each account is tied to the specific site domain.
What languages are supported?
We support 23 languages: Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish. Any voice can speak any of these languages. If language is not set, it is guessed from the script.
Can I use my own voice?
No. We do not offer custom voice cloning, uploading your own voice, or voice design. The eight presets are based on licensed recordings from LibriTTS-R and LibriVox public-domain audiobook readings. Every generated file carries an inaudible watermark marking it as synthetic speech.
How much does it cost?
Pricing is $10 per 1 million characters, or $0.01 per 1,000 characters. Spaces and punctuation count as characters. Failed requests are free, with charges returned in full. There are no monthly plans, seats, or minimum spend requirements.
Is there a free trial?
Yes. Signing in with Google provides $0.50 of credit, valid for 7 days, covering about 50,000 characters. Accounts created with email and password start without trial credit. The balance does not expire, and top-ups are processed automatically.
What audio formats are available?
You can choose from mp3, wav, opus, flac, and pcm. These formats are selected via the response_format field in the API request. The API returns the generated audio file directly in the response for immediate use in your educational materials.
How long is the input text?
Each request accepts up to 4096 characters. For longer texts, split them into parts of this limit and join the resulting audio files. Typical speed is roughly real time, processing about 25 characters per second, though requests may queue under load.
Do you offer SSML?
No. The API does not support SSML, phoneme dictionaries, or custom pronunciation lexicons. It uses a straightforward REST endpoint with simple parameters for model, input, voice, format, and speed. This keeps the integration simple for no-code users in schools.
Is the API reliable for schools?
We do not offer an SLA or uptime guarantee. Requests are processed sequentially, so under load, a request may wait in a queue. Typical speed is roughly real time. We provide support by email only, with no phone or live chat.
How are voices licensed?
Voices are based on licensed recordings: LibriTTS-R (CC BY 4.0), from LibriVox public-domain audiobook readings. The eight presets include female and male options like Aria, Nova, Felix, and Milo. Each generated file includes an inaudible watermark identifying it as synthetic speech.
Can I stream audio?
No. We do not offer streaming, WebSocket connections, or real-time partial audio. The API returns the complete audio file after synthesis is finished. This fits standard REST workflows for downloading lesson audio files rather than live playback scenarios.
What happens if a request fails?
If synthesis fails, the charge is returned in full. You are not billed for failed requests. You can retry the request or adjust parameters like voice or format. The API ensures you only pay for successfully generated audio files.
How do I top up my balance?
Top up using USDT on the TRON network (TRC-20). The minimum amount is $5. Credits are credited automatically within minutes after the transfer. We do not accept cards, PayPal, or subscriptions. Balance does not expire.
First request
curl
curl https://api.playnn77.com/v1/audio/speech \
-H "Authorization: Bearer $TTS_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"tts-1","voice":"aria","input":"Hello from the API.","response_format":"mp3"}' \
--output hello.mp3How the TTS API Works
Lectura converts lesson text, reading materials, and announcements into audio files. You send a text string to our endpoint and receive a single audio file in return. The system handles character splitting up to 4096 characters and joins the resulting parts automatically.
Send Text, Receive Audio
Input your text via a simple POST request. The API processes the input and returns the synthesized audio file directly in the response. Failed requests incur no charge.
Standard REST Endpoint
Use the standard REST endpoint at POST https://api.playnn77.com/v1/audio/speech. The request body uses JSON, matching the shape of the OpenAI speech endpoint. This allows you to use the official OpenAI SDKs by simply changing the base_url to https://api.playnn77.com/v1.
No Coding Required
Teachers can use the provided cURL examples or the dashboard interface to generate audio. The API handles the technical details of synthesis, format selection, and audio joining. No custom integration code is needed for basic usage.
Voices and Languages
Lectura provides eight preset voices, each with a distinct tone suitable for different classroom contexts. Options range from warm narrators and upbeat announcers to calm instructors and deep documentary styles, allowing teachers to match the audio to the lesson's mood.
8 Preset Voices
Female voices include Aria (warm narrator), Nova (bright), Luna (soft storytelling), and Sage (calm instruction). Male options feature Felix (energetic promo), Milo (friendly conversation), Atlas (neutral news), and Orion (deep documentary).
All voices are based on licensed recordings from LibriTTS-R and LibriVox. Every generated file contains an inaudible watermark identifying it as synthetic speech.
- Aria: Warm, clear narrator
- Nova: Bright, upbeat
- Luna: Soft, storytelling
- Sage: Calm, instructional
- Felix: Energetic, promo
- Milo: Friendly, conversational
- Atlas: Neutral, news
- Orion: Deep, documentary
23 Supported Languages
The API supports 23 languages, including Arabic, Chinese, Danish, Dutch, English, Finnish, French, German, Greek, Hebrew, Hindi, Italian, Japanese, Korean, Malay, Norwegian, Polish, Portuguese, Russian, Spanish, Swahili, Swedish, and Turkish.
Any voice can speak any of these languages. Unsupported languages include Vietnamese, Indonesian, Thai, Ukrainian, Romanian, and Czech.
Automatic Language Detection
If the language field is not set, the system guesses the language from the text script. Latin script text defaults to English.
For non-English Latin-script text, explicitly set the language parameter to ensure accurate pronunciation and delivery.
Audio Formats and Quality
The API supports standard audio formats including MP3, WAV, OPUS, and FLAC, allowing flexible integration into school learning management systems and accessibility tools. You select the format via the response_format parameter in your JSON request.
Generated audio files are returned directly in the response and are not stored on our servers. This ensures immediate delivery without cluttering your school's storage infrastructure.
MP3, WAV, OPUS, FLAC
Choose the format that best fits your classroom technology. MP3 offers high compression for web playback, while WAV and FLAC provide lossless quality for archival purposes. OPUS is an efficient format for modern browsers.
Real-Time Speed
Audio generation typically processes at roughly real-time speed, generating about 25 characters of text per second. Short phrases may take a few seconds, while longer texts are split and joined seamlessly. Under load, requests may wait in a queue.
Synthetic Watermarking
Every generated audio file contains an inaudible watermark marking it as synthetic speech. This helps identify audio produced by the Lectura API without affecting playback quality or user experience.
Pricing for Education
Lectura charges $0.01 per 1,000 characters, including spaces and punctuation. This linear model fits school budgets without unexpected overages or minimum spend requirements. You only pay for successful synthesis; failed requests are refunded in full.
Pay Per Character
The rate is $10 per million characters. This straightforward metric makes it easy to estimate costs for lesson plans or reading materials based on character count.
- $10 per 1,000,000 characters
- $0.01 per 1,000 characters
- Spaces and punctuation count
Free Trial Credit
Signing in with Google provides $0.50 in credit, valid for 7 days. This allows educators to test the API with approximately 50,000 characters before committing to a top-up.
- $0.50 trial credit
- 7-day validity
- Google sign-in only
No Monthly Fees
There are no subscriptions, seats, or recurring bills. You top up via USDT (TRC-20) when needed. The balance does not expire, so unused funds remain available for future semesters.
- No monthly plans
- No seat limits
- Balance never expires
Data Privacy and Training
Lectura is designed for educational environments where student data privacy is paramount. When you send text to the API, the input is used exclusively for the immediate generation of the audio file. We do not use your input text for training. This ensures that your curriculum content remains private and distinct from public training datasets.
No Training Usage
The text you provide is processed solely to produce the requested audio output. It is not ingested into our training data pool, meaning your school’s specific materials do not influence future model versions. This separation guarantees that proprietary or sensitive educational content remains isolated from model development.
No Data Storage
Generated audio files are returned directly in the API response and are not stored on our servers after delivery. Request metadata (time, characters, status) is kept for billing. This minimizes the risk of data exposure from long-term storage, ensuring that once the audio is downloaded, the raw data is gone.
Metadata for Billing
We retain only the essential metadata required for accurate billing and service management. This includes the timestamp of the request, the character count processed, and the status of the synthesis (e.g., success or failure). No content metadata or usage patterns beyond billing needs are kept.
- Request time and status
- Character count per request
- Billing records only

Integration Options
Lectura uses a standard REST endpoint compatible with the OpenAI SDK. Update your base URL to https://api.playnn77.com/v1 and use your API key to generate audio without custom libraries.
The JSON request structure mirrors official speech endpoints. Send text, select a voice, and specify the output format. The API returns the audio file directly in the response.
OpenAI SDK Compatible
Use the official OpenAI SDK by changing the base_url to https://api.playnn77.com/v1. Authenticate with your tts-... key in the Authorization header. This allows immediate integration with existing Python or Node.js scripts without rewriting request logic.
cURL Examples
For quick testing, use cURL to send a POST request to the v1/audio/speech endpoint. Include the Authorization header with your Bearer token and the JSON body containing model, input, voice, and response_format.
- Replace
YOUR_API_KEYwith your actual key. - Set
modeltotts-1ortts-1-hd. - Specify
voicefrom the 8 available presets. - Set
response_formatto mp3, wav, opus, flac, or pcm.
JSON Body Structure
The request body is a simple JSON object. Required fields include model, input (text up to 4096 characters), voice, and response_format. Optional fields like speed (0.25–4.0) and language (ISO code) allow customization.
Rate Limits and Reliability
Lectura’s API handles request volume with a standard rate limit of 60 requests per minute per API key. New accounts start with a lower threshold of 10 requests per minute until the first top-up is processed. This ensures stable performance for classroom use without requiring complex infrastructure management.
60 Requests Per Minute
Each API key is allowed up to 60 synthesis requests per minute. If your key is new, this limit is temporarily reduced to 10 requests per minute. The limit increases automatically once you add funds via USDT (TRC-20). This cap applies to all request types, regardless of audio length or format.
- Standard limit: 60 requests/minute per key.
- New account limit: 10 requests/minute.
- Limit resets every 60 seconds.
- Applies to both tts-1 and tts-1-hd models.
Queue Processing
Requests are processed sequentially. If you send multiple requests quickly, they are queued and handled one after another. Longer texts take more time to generate, roughly 25 characters per second of audio. Short phrases may take a few seconds to complete.
Character Limits
Each API request accepts a maximum of 4096 characters of input text. Spaces and punctuation count toward this limit. For lesson texts or books longer than 4096 characters, split the text into parts, generate each part, and join the resulting audio files.
- Max input: 4096 characters per request.
- Spaces and punctuation count as characters.
- Split longer texts manually for multi-part audio.
Support and Contact
Lectura provides email-only support for all schools and teachers using the API. We do not offer phone lines, live chat, or instant messaging, ensuring that queries are handled systematically without interruption during class hours.
Account management is straightforward: each account holds one active API key. You can issue a new key at any time via the dashboard, and the previous key stops working immediately, maintaining security without administrative overhead.
Email Support Only
All inquiries are managed via email. There is no phone number to call, and we do not maintain live chat widgets on this site. This approach keeps support costs low, allowing us to offer competitive per-character pricing for educational institutions.
No Live Chat
We have chosen to forgo live chat to avoid fragmented communication. Instead, detailed technical questions and billing issues are addressed via email, allowing for clear, documented responses that you can reference later.
Key Management
Each account is tied to a single active API key. If you suspect a leak or need to rotate credentials, you can generate a new key at any time. The old key becomes invalid instantly, ensuring no concurrent usage with different permissions.
- Generate new keys instantly via the dashboard
- Old keys stop working immediately upon rotation
- One key per account for simple tracking
Common Use Cases
Lectura converts lesson texts and reading materials into audio files.
Reading Materials
Teachers can upload chapter texts or articles up to 4096 characters per request. The API processes these inputs to generate MP3 or WAV files that students can listen to during commutes or study sessions, supporting 23 languages for diverse classrooms.
- Convert textbook chapters to audio for independent study
- Support multilingual classrooms with automatic language detection
- Generate audio files compatible with standard media players
Class Announcements
School administrators can turn daily schedules, event notices, or emergency alerts into audio announcements. By using preset voices like Felix or Atlas, schools can generate audio files for announcements or send audio links via email to parents and staff.
- Create consistent daily schedule audio files
- Broadcast emergency alerts in multiple languages
- Send audio links to parents and staff via email
Accessibility Tools
Provide auditory access to written content for students with dyslexia or visual impairments. Lectura’s synthetic speech includes an inaudible watermark to identify generated audio, helping institutions maintain transparency about content origins while ensuring all students can access the same educational materials.
- Support students with dyslexia or visual impairments
- Identify synthetic speech with inaudible watermarking
- Ensure equal access to written educational materials
Listen to the 8 voices
Each sample below was generated by this API from the same sentence. Teachers can easily design engaging lessons without needing technical skills to manage their classrooms efficiently.
23 languages
Any voice speaks any of these languages.
